{"id":17891505,"url":"https://github.com/amanpriyanshu/dp-hyperparamtuning","last_synced_at":"2025-10-19T06:25:01.294Z","repository":{"id":37434514,"uuid":"391169007","full_name":"AmanPriyanshu/DP-HyperparamTuning","owner":"AmanPriyanshu","description":"DP-HyperparamTuning offers an array of tools for fast and easy hypertuning of various hyperparameters for the DP-SGD algorithm.","archived":false,"fork":false,"pushed_at":"2021-09-27T09:20:22.000Z","size":91,"stargazers_count":24,"open_issues_count":0,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-18T14:23:00.112Z","etag":null,"topics":["automl","hyperparameter-optimization","machine-learning","pytorch","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AmanPriyanshu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-07-30T19:21:04.000Z","updated_at":"2024-07-30T01:33:53.000Z","dependencies_parsed_at":"2022-08-19T17:00:45.058Z","dependency_job_id":null,"html_url":"https://github.com/AmanPriyanshu/DP-HyperparamTuning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FDP-HyperparamTuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FDP-HyperparamTuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FDP-HyperparamTuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FDP-HyperparamTuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AmanPriyanshu","download_url":"https://codeload.github.com/AmanPriyanshu/DP-HyperparamTuning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245020147,"owners_count":20548154,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["automl","hyperparameter-optimization","machine-learning","pytorch","reinforcement-learning"],"created_at":"2024-10-28T14:17:46.611Z","updated_at":"2025-10-19T06:25:01.207Z","avatar_url":"https://github.com/AmanPriyanshu.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DP-HyperparamTuning\n\nThe offical repository for all algorithms and code for the [Efficient Hyperparameter Optimization for Differentially Private Deep Learning](https://arxiv.org/abs/2108.03888) accepted at [PPML Workshop @ ACM-CCS'2021](https://ppml-workshop.github.io/).\n\nA streamlined and basic implementation for all modules presented is available at:\n\n* [GitHub Repo](https://github.com/AmanPriyanshu/DP-HyperparamTuning)\n* [GitHub Notebook](https://github.com/AmanPriyanshu/DP-HyperparamTuning/blob/main/RL_DP_Demo.ipynb)\n\n`Note:` [Colab Demo for the same](https://colab.research.google.com/github/AmanPriyanshu/DP-HyperparamTuning/blob/main/RL_DP_Demo.ipynb)\n\n# Implementation:\n\n## Imports:\n\n```python\nfrom DP_HyperparamTuning.experiment.train_single_model import Experiment\nfrom DP_HyperparamTuning.algorithms.bayesian_optimization import Bayesian\nfrom DP_HyperparamTuning.algorithms.grid_search_algorithm import GridSearch\nfrom DP_HyperparamTuning.algorithms.evolutionary_optimization import EvolutionaryOptimization\nfrom DP_HyperparamTuning.algorithms.reinforcement_learning_optimization import RLOptimization\n```\n\n## Running Given Modules:\n\n```python\ne = Experiment(get_model, criterion, train_dataset, test_dataset)\nb = Bayesian(e.run_experiment, calculate_reward, num_limit, search_space_nm=search_space_nm, search_space_lr=search_space_nm)\n```\n\nWhere, `get_model`, `calculate_reward` are functions, and `criterion` and `train_dataset, test_dataset` which are `\u003cclass 'torch.nn.modules.loss.BCELoss'\u003e` and `torch.utils.data.Dataset` respectively.\n\n# Contributing\n\nWhen contributing to this repository, please first discuss the change you wish to make via issue,\nemail, or any other method with the owners of this repository before making a change. We also make\navailable a [CONTRIBUTING.md](https://github.com/AmanPriyanshu/DP-HyperparamTuning/blob/main/CONTRIBUTING.md) and [CODE_OF_CONDUCT.md](https://github.com/AmanPriyanshu/DP-HyperparamTuning/blob/main/CODE_OF_CONDUCT.md) for easy communication and quick issue resolution.\n\n# Paper Citation:\n\n```bib\n@misc{priyanshu2021efficient,\n      title={Efficient Hyperparameter Optimization for Differentially Private Deep Learning}, \n      author={Aman Priyanshu and Rakshit Naidu and Fatemehsadat Mireshghallah and Mohammad Malekzadeh},\n      year={2021},\n      eprint={2108.03888},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famanpriyanshu%2Fdp-hyperparamtuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famanpriyanshu%2Fdp-hyperparamtuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famanpriyanshu%2Fdp-hyperparamtuning/lists"}